← Back to all news
arXiv AI By Liu Hung Ming

Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning

Read the original on arXiv AI →

The paper introduces a protocol for auditing and composing reinforcement‑learning policies using discrete behavioral rules, defining auditability through six testable predicates such as trace integrity and rule coverage. Experiments show that overlapping rule sets do not guarantee behavioral agreement, and that rule‑based fusion often fails to outperform value‑based composition, highlighting limitations in current description layers. The authors provide an evidence‑bounded audit framework and outline future directions for more robust skill composition.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 18

AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment

AUDITPLAN introduces a plan-then-answer method for safety alignment in language models, where the model first generates a compact structured safety plan before responding. The plan includes a threat label, intended action, and explicit constraints, allowing machine‑checkable auditing while remaining hidden from end users. Training combines supervised fine‑tuning with reinforcement learning using the FAITHGATE reward, which only rewards correct plans, thereby reducing unsafe shortcuts and improving robustness across Qwen model variants.

By Sai Sri Pushpa Jampani, Kshitij Mishra, Asif Ekbal
reinforcement-learningfine-tuningmultimodalsafety
More like this →
arXiv AI
Aug 24

No Judgment Without a Reason: Counterfactual Receipts for Versioned AI Evaluators

The paper introduces a framework for evaluating AI systems that not only checks final labels but also tracks the reasoning behind them through three core sources—grounds, norms, and authority—forming an eight-cell counterfactual judgment cube. It defines minimal source replacement sets, called judgment receipts, to explain changes in verdicts and provides certification cost bounds for black-box evaluators. The authors present ReasonBench, a benchmark with 19,520 cases, and demonstrate that while high standard accuracy can mask robustness issues, receipt accuracy reveals significant gaps in reasoning consistency across different models.

By Ye Chen, Weining Zhang
agentsbenchmarks
More like this →